wait-what
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security threats identified. The skill instructs the agent to adopt a specific communication style (ASD-STE100) and reference internal documentation (GLOSSARY.md, GLOSSARY-MAP.md) to clarify context. The skill configuration explicitly disables model invocation, which prevents the agent from calling any tools or executing commands based on the instructions or referenced data.- [INDIRECT_PROMPT_INJECTION]: The skill processes content from repository files to guide its output style, creating a minimal ingestion surface.\n
- Ingestion points: The skill reads terminology and mapping instructions from GLOSSARY.md and GLOSSARY-MAP.md.\n
- Boundary markers: None specified for the ingested file content.\n
- Capability inventory: None. The skill has disable-model-invocation set to true, preventing any functional exploitation (file writes, network calls, or command execution) from being triggered by the ingested content.\n
- Sanitization: None specified for the ingested files.
Audit Metadata